Content area

Abstract

Background

The clinical potential of Raman spectroscopy is well established but has yet to become established in routine oncology workflows. One barrier slowing clinical adoption is a lack of evidence demonstrating that data taken on one spectrometer transfers across to data taken on another spectrometer to provide consistent diagnoses.

Methods

We investigated multi-centre transferability using human oesophageal tissue. Raman spectra were taken across three different centres with different spectrometers of the same make and model. By using a common protocol, we aimed to minimise the difference in machine learning performance between centres.

Results

61 oesophageal samples from 51 patients were interrogated by Raman spectroscopy at each centre and classified into one of five pathologies. The overall accuracy and log-loss did not significantly vary when a model trained upon data from any one centre was applied to data taken at the other centres. Computational methods to correct for the data during pre-processing were not needed.

Conclusion

We have found that when using the same make and model of spectrometer, together with a common protocol, across different centres it is possible to achieve system transferability without the need for additional computational instrument correction.

Details

Title
System transferability of Raman-based oesophageal tissue classification using modern machine learning to support multi-centre clinical diagnostics
Author
Blake, Nathan 1   VIAFID ORCID Logo  ; Gaifulina, Riana 1 ; Isabelle, Martin 2 ; Dorney, Jennifer 3 ; Rodriguez-Justo, Manuel 4 ; Lau, Katherine 5 ; Ohrel, Stéphanie 5 ; Lloyd, Gavin 6 ; Shepherd, Neil 7 ; Lewis, Aaran 1 ; Kendall, Catherine A. 6 ; Stone, Nick 3 ; Bell, Ian 5 ; Thomas, Geraint 1 

 University College London, Department of Cell and Developmental Biology, London, UK (GRID:grid.83440.3b) (ISNI:0000 0001 2190 1201) 
 Adaptimmune Therapeutics Plc, Translational Sciences, Abingdon, UK (GRID:grid.83440.3b) 
 University of Exeter, Biomedical Physics, Department of Physics and Astronomy, Exeter, UK (GRID:grid.8391.3) (ISNI:0000 0004 1936 8024) 
 University College London, Department of Research Pathology, Cancer Institute, London, UK (GRID:grid.83440.3b) (ISNI:0000 0001 2190 1201) 
 Renishaw PLC, New Mills, Spectroscopy Products Division, Wotton-under-Edge, UK (GRID:grid.51580.39) (ISNI:0000 0004 0395 8863) 
 Gloucestershire Hospitals NHS Foundation Trust, Biophotonics Research Unit and Pathology Department, Gloucester, UK (GRID:grid.434530.5) (ISNI:0000 0004 0387 634X) 
 Cheltenham General Hospital, Gloucestershire Cellular Pathology Laboratory, Cheltenham, UK (GRID:grid.413842.8) (ISNI:0000 0004 0400 3882) 
Pages
52
Publication year
2024
Publication date
Dec 2024
Publisher
Nature Publishing Group
e-ISSN
27319377
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
3225848011
Copyright
Copyright Nature Publishing Group Dec 2024